Autonomous Control and Guidance for an Underwater Robotic Vehicle

Abstract

Underwater robots require adequate guidance and control to perform useful tasks. Visual information is important to these tasks and visual servo control is one method by which guidance can be obtained. To coordinate and control thrusters, complex models and control schemes can be replaced by a connectionist learning approach. Reinforcement learning uses a reward signal and much interaction with the environment to form a policy of correct behavior. By combining vision-based guidance with a neurocontroller trained by reinforcement learning our aim is to enable an underwater robot to hold station on a reef or swim along a pipe.